© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 368
    Prev
    Next
    INDEX
    Explanations

    relaxation and humidity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attro
    -0.31
    uze
    -0.29
     witnessing
    -0.28
    JKLMNOP
    -0.28
    formats
    -0.26
    âĩĵ
    -0.25
    é£İåij³
    -0.25
    ÙĩÙĬ
    -0.25
     tabindex
    -0.24
    çĮ®
    -0.24
    POSITIVE LOGITS
    enced
    0.30
    âľĸ
    0.27
    lots
    0.26
    ences
    0.26
    æľĪ以æĿ¥
    0.25
    èĤ¥
    0.24
     die
    0.24
    encer
    0.23
    าว
    0.23
     Sheet
    0.23
    Activations Density 0.015%

    No Known Activations